MDMatthew Davis

Matthew Davis

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Matthew Davis has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Leveraging Large Language Models for Automated Extraction of Abdominal Aortic Aneurysm Features from Radiology Reports

    by Praneel Mukherjee, Ryan C. Lee, Roham Hadidchi, Sonya Henry, Michael Coard, Matthew Davis, Yossef Rubinov, Ha Nguyen-Luong, Leah Katz, Tim Q. Duong

    Background/Objectives. Abdominal computed tomography (CT) radiology reports contain critical information for abdominal aortic aneurysm (AAA) management, including aneurysm presence, size, rupture status, and prior repair. However, this information is often embedded within lengthy, heterogeneous reports, making manual extraction inefficient. We evaluated the performance of multiple large language models (LLMs) for automated extraction of AAA-related findings from radiology reports. Methods. We retrospectively analyzed 500 abdominal CT reports mentioning AAA from an urban academic health system (2020–2024). Ground truth labels were established by manual review. Four open-source LLMs (Qwen2.5-7B-Instruct, Llama3-Med42-8B, GPT-OSS-20B, and MedGemma-27B-text-it) were evaluated for extraction of aneurysm presence, size, morphology, rupture status, impending rupture, and prior aortic repair. Model outputs were compared with ground truth using exact-match accuracy, and inter-model agreement was assessed using Fleiss’ kappa. Reasoning traces were examined to characterize correct and incorrect model behavior. Results. Accuracy for identifying AAA presence ranged from 0.90 to 0.95 (κ = 0.851), and prior aortic repair from 0.90 to 0.97 (κ = 0.793). Accuracy for aneurysm size ranged from 0.67 to 0.88 (κ = 0.340), with low κ’s due to class imbalance or dimension misselection. Rupture and impending rupture were identified with accuracies exceeding 0.90 across models, though agreement was lower (κ = 0.485 and 0.589), reflecting low event prevalence. Larger models (GPT-OSS-20B, MedGemma-27B) generally outperformed smaller models. Reasoning analysis revealed strengths in measurement prioritization but recurrent errors, including dimension misselection, over-inference of prior repair, and conservative classification of rupture-related findings. Conclusions. LLMs can accurately extract clinically relevant AAA information from radiology reports with interpretable reasoning, with larger and medically trained models outperforming smaller or general-purpose models. Performance varies by task and model, underscoring the need for careful validation and human-in-the-loop deployment in clinical settings.

  • Open Access

    Analysis of Neutrophil/Lymphocyte Ratio as a Potential Biomarker Stratified by Breast Cancer Histologic Subtype

    by Emily Hunt, Matthew Davis, Wei Hou, Henrietta Bains, Timothy Darby, Julia Hou, Julie Chung, Roham Hadidchi, Tim Q. Duong, Takouhie Maldjian

    Background/Objectives: Breast cancer is the most common cancer in women. The neutrophil/lymphocyte ratio (NLR) is an emerging biomarker from peripheral blood that has been associated with breast cancer prognosis in some studies; however, some studies fail to demonstrate an association. We stratified breast cancer patients into invasive lobular carcinoma (ILC) and invasive ductal carcinoma (IDC) cohorts to evaluate if any meaningful association could be found in either cohort between NLR and mortality. Additionally, no prior studies have examined the relationship between NLR and background parenchymal enhancement (BPE) on breast MRI, an imaging feature linked to increased breast cancer risk and a potential imaging prognostic biomarker, so we examined the relationship between BPE and NLR in the two cohorts. Methods: This retrospective study included 794 breast cancer patients who had either IDC or ILC. Radiologists’ MRI reports and their BI-RADS categorization of BPE (1 = minimal, 2 = mild, 3 = moderate, 4 = marked) were extracted and recorded. The NLR was calculated from blood counts obtained prior to treatment. Tumor characteristics were also recorded. Results: For patients with ILC, NLR was found to be associated with mortality. Additionally, patients with ILC and a high BPE had a significantly higher mean NLR compared to all other groups, including low BPE groups and all IDC groups. Conclusions: There is potential value in using NLR, a readily available blood biomarker, in models predicting prognosis in ILC patients.